Check Agent Compatibility

This runs a four-part compatibility check to tell you how well a repository works with AI coding agents. It spins up separate subagents to test the scanner score, whether an agent can actually boot the repo, whether it can verify a small change without spinning forever, and whether the docs match reality. You get back a single weighted score and a flat list of the top fixes that would actually help agent workflows. The scoring blends deterministic analysis with behavioral checks and explicitly avoids penalizing repos for noisy logs or rough error messages. Use it when you need to know if a codebase is agent-friendly or what friction points to fix first.

skills.sh installs: 4
GitHub stars: 2.1K
last updated: Jun 23, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill check-agent-compatibility --agent claude-code

Installs into .claude/skills of the current project.

Files

Check agent compatibility

Trigger

Use when the user wants the full compatibility pass for a repo.

Workflow

Launch compatibility-scan-review to run the CLI and capture the raw repository score and main issues.
Launch startup-review to verify whether the repo can actually be booted by an agent.
Launch validation-review to check whether an agent can verify a small change without an unnecessarily heavy loop.
Launch docs-reliability-review to see whether the documented setup and run paths reliably match reality.
Use one subagent per task. Do not collapse these checks into one agent prompt.
Compute an internal workflow score as the rounded average of:
- Startup Compatibility Score
- Validation Loop Score
- Docs Reliability Score
Compute an Agent Compatibility Score as:
- round((deterministic_score * 0.7) + (workflow_score * 0.3))
Synthesize the results into one final response.